# GLM-5.1 vs Nemotron 3 Super

> GLM-5.1 is the stronger model overall, scoring 47.6 to 39.6 on the Noometry Index. Nemotron 3 Super costs 12× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-nemotron-3-super
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Nemotron 3 Super in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 38.2 to 17.9.
- The biggest single-benchmark swing is NYT Connections (extended): 77.7% for GLM-5.1 and 15.4% for Nemotron 3 Super.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Nemotron 3 Super accepts more context: 262K tokens versus 200K.

## Snapshot

| | GLM-5.1 | Nemotron 3 Super |
|---|---|---|
| Provider | Z.ai (Zhipu) | NVIDIA |
| Noometry Index | 47.6 | 39.6 |
| Rank | 51 | 147 |
| Context | 200K | 262K |
| Input $/M | $1.40 | $0.08 |
| Output $/M | $4.40 | $0.45 |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.5 (#52)
- Nemotron 3 Super: 38.9 (#153)

| Benchmark | GLM-5.1 | Nemotron 3 Super |
|---|---|---|
| SciCode | 43.8% | 36% |
| WeirdML | 57.1% | 38% |
| LMArena Coding | 1486 | 1403 |
| ALE-Bench | 887.1 | 213.9 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1509 | — |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- Nemotron 3 Super: —

| Benchmark | GLM-5.1 | Nemotron 3 Super |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- Nemotron 3 Super: 17.9 (#274)

| Benchmark | GLM-5.1 | Nemotron 3 Super |
|---|---|---|
| NYT Connections (extended) | 77.7% | 15.4% |
| CritPt | 4.6% | 3.1% |
| LMArena Hard Prompts | 1472 | 1386 |
| SimpleBench | 55.1% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| Epoch Capabilities Index | 149.86 | — |

## Math

- GLM-5.1: 49.0 (#48)
- Nemotron 3 Super: 37.6 (#95)

| Benchmark | GLM-5.1 | Nemotron 3 Super |
|---|---|---|
| MathArena Final-Answer Competitions | 67.1% | 60.4% |
| LMArena Math | 1472 | 1381 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 55.0 (#45)
- Nemotron 3 Super: 38.2 (#136)

| Benchmark | GLM-5.1 | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1477 | 1397 |
| GPQA Diamond | 89.9% | — |
| SimpleQA Verified | 34% | — |

## Multilingual

- GLM-5.1: 55.2 (#34)
- Nemotron 3 Super: 48.6 (#139)

| Benchmark | GLM-5.1 | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1448 | 1356 |
| LMArena Chinese | 1516 | 1430 |
| LMArena French | 1478 | 1404 |
| LMArena German | 1466 | 1341 |
| LMArena Russian | 1453 | 1336 |
| LMArena Spanish | 1467 | 1417 |
| LMArena Japanese | 1436 | — |
| LMArena Korean | 1423 | — |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- Nemotron 3 Super: 71.4 (#149)

| Benchmark | GLM-5.1 | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1451 | 1347 |

## Long Context

- GLM-5.1: 44.9 (#51)
- Nemotron 3 Super: 41.5 (#134)

| Benchmark | GLM-5.1 | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1467 | 1362 |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- Nemotron 3 Super: 56.1 (#135)

| Benchmark | GLM-5.1 | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1462 | 1378 |
| LMArena Creative Writing | 1454 | 1317 |
| LMArena Multi-Turn | 1473 | 1369 |
| EQ-Bench Creative Writing | 1592 | — |

## FAQ

### Is GLM-5.1 better than Nemotron 3 Super?

GLM-5.1 is the stronger model overall, scoring 47.6 to 39.6 on the Noometry Index. Nemotron 3 Super costs 12× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

### Which is cheaper, GLM-5.1 or Nemotron 3 Super?

Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.

### Is GLM-5.1 or Nemotron 3 Super better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 38.9 in the Noometry coding category.

### Which has the bigger context window?

Nemotron 3 Super does, with 262K tokens against 200K.

### How many benchmarks do GLM-5.1 and Nemotron 3 Super share?

21 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Nemotron 3 Super has 21.